Finally, error reduction rates for the four two-stage models relative to their corresponding single-stage models ranging from 1 to 8 are averaged, respectively, resulting in Table 7. It indicates that the performance of SVR–Ridge and SVR–SVR is significantly improved than Ridge and SVR, respectively. The performance of SVR–ANN is moderately improved than ANN and SVR–RF is slightly improved than RF. This demonstrates the advantages of the proposed two-stage procedure.
Average reduced rates of the four two-stage approaches vs. the four single-stage approaches
| Models . | RMSE . | MAE . |
|---|---|---|
| SVR–SVR vs. SVR (%) | 36.06 | 36.06 |
| SVR–RF vs. RF (%) | 5.98 | 6.91 |
| SVR–Ridge vs. Ridge (%) | 43.05 | 43.27 |
| SVR–ANN vs. ANN (%) | 14.81 | 15.35 |
| Models . | RMSE . | MAE . |
|---|---|---|
| SVR–SVR vs. SVR (%) | 36.06 | 36.06 |
| SVR–RF vs. RF (%) | 5.98 | 6.91 |
| SVR–Ridge vs. Ridge (%) | 43.05 | 43.27 |
| SVR–ANN vs. ANN (%) | 14.81 | 15.35 |